© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93577
    Prev
    Next
    INDEX
    Explanations

    concept and related term

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    -1.36
    えっ
    -1.34
    為に
    -1.34
    あぁ
    -1.24
    あー
    -1.21
     juſ
    -1.16
    のいい
    -1.15
    の良い
    -1.13
    conocimiento
    -1.11
     verlangt
    -1.10
    POSITIVE LOGITS
    <bos>
    1.43
     in
    1.39
    JAH
    1.04
     Hälfte
    1.04
    purple
    1.04
    Kontrola
    1.03
    THA
    1.03
     emblema
    1.01
     向け
    0.99
     ۱۵
    0.99
    Activations Density 0.351%

    No Known Activations